Zhen Fang

CostaliyA's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 16 hours ago

FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis

Paper • 2608.18580 • Published 2 days ago • 2

upvoted a paper 7 days ago

AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design

Paper • 2608.13560 • Published 8 days ago • 52

upvoted a paper 9 days ago

SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information

Paper • 2608.10692 • Published 10 days ago • 12

upvoted 3 papers 10 days ago

Evo-Bench: Can Language Models Improve Agent Harness?

Paper • 2608.09096 • Published 11 days ago • 18

Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning

Paper • 2608.03571 • Published 15 days ago • 43

SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation

Paper • 2608.04419 • Published 16 days ago • 28

upvoted 2 papers 11 days ago

AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

Paper • 2608.05987 • Published 15 days ago • 97

Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning

Paper • 2608.02831 • Published 18 days ago • 13

upvoted 2 papers 16 days ago

Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging

Paper • 2608.03316 • Published 17 days ago • 26

Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent

Paper • 2608.03979 • Published 17 days ago • 51

upvoted a paper 17 days ago

LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks

Paper • 2608.01964 • Published 18 days ago • 176

upvoted a paper 21 days ago

VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System

Paper • 2607.27380 • Published 23 days ago • 71

upvoted a paper 24 days ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 25 days ago • 497

upvoted an article 25 days ago

view article

Article

Kimi K3 Model Overview: 2.8T Parameters, MXFP4 Quantization, and What the Open Weights Mean for the Community

• 

ResterChed

•

Jul 17

• 197

upvoted a paper 29 days ago

Self Gradient Forcing: Native Long Video Extrapolation

Paper • 2607.20368 • Published 30 days ago • 36

upvoted 4 papers about 1 month ago

TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs

Paper • 2607.17423 • Published Jul 19 • 167

SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2607.14777 • Published Jul 16 • 106

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

Paper • 2607.14935 • Published Jul 16 • 172

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Paper • 2607.07675 • Published Jul 8 • 64

upvoted a paper about 2 months ago

In-Context World Modeling for Robotic Control

Paper • 2606.26025 • Published Jun 25 • 63